adr-index
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
node plugins/ruflo-adr/scripts/import.mjs. This script is responsible for parsing documentation files and indexing them into a memory store. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes content from the project's ADR files.
- Ingestion points: Reads files from
*/docs/adr/and*/docs/adrs/(SKILL.md). - Boundary markers: None observed in the parsing logic description.
- Capability inventory: Uses
Bashto run node scripts and utilizes MCP memory tools for storage and search (SKILL.md). - Sanitization: Employs regex to strip issue/PR/commit references to ensure edge-detection accuracy, but does not implement security-specific sanitization of the processed text content.
Audit Metadata